Michael Antolovich

Papers

Total Citations

H-Index

About

Dr. Michael Antolovich is a researcher specializing in robotics and machine learning, with a particular focus on **Learning from Demonstration (LfD)** for autonomous systems in challenging environments. His major contributions lie in applying probabilistic models—such as **Gaussian Mixture Models (GMM), Continuous and Discrete Hidden Markov Models (CHMM and DHMM)**—to enable robots to learn complex tasks from human demonstrations. Dr. Antolovich’s work is notably applied to **mining tunnel inspection robots**, where he developed novel training dataset selection methods like **Information Extraction (IE)** to improve learning efficiency and robustness. His most cited paper, *“Robot learning by a mining tunnel inspection robot”* (2012, 6 citations), demonstrates how DHMM can train a robot to perform inspection tasks autonomously after only a few demonstrations. Across his research, Dr. Antolovich has systematically compared LfD kernels and variable selection techniques, advancing the field’s understanding of how to make robot learning more practical and reliable in real-world, unstructured settings. His work bridges theoretical machine learning with applied robotics, offering valuable insights for students and researchers interested in autonomous systems, human-robot interaction, and industrial automation.